Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses that the rule applies immediately to past and future transactions, is case-insensitive, and returns a count of recategorized transactions. Annotations already indicate idempotent and non-destructive, and description aligns with these.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single paragraph, front-loaded with the action, then details and example. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 2 parameters, no output schema, and adequate annotations, the description fully covers purpose, behavior, usage, and provides an example, making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters have descriptions in the schema, but the description adds context (case-insensitive matching) and an example that clarifies usage beyond schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a rule that assigns a category to transactions matching a substring, and distinguishes from sibling tools like finance_list_category_rules and finance_remove_category_rule.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use this to clean up transactions stuck in other' and provides a concrete example, but does not explicitly state when not to use the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses key behaviors: fresh fetch per call with caching, sign convention for credit/loan balances, fallback to cached data with note. No annotation contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences covering purpose, source, caching, sign convention, error handling, and return structure. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters, no output schema, the description provides a detailed return structure and error handling. Fully adequate for an agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters; description explicitly notes 'No args.' Schema coverage is 100%, so description adds value by confirming no input needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it returns live per-account balances and net worth via SimpleFIN. Differentiates from sibling tools by specifying real-time nature and caching behavior. No ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States prerequisite (requires finance_link_bank first) and fallback behavior when live fetch fails. Could explicitly mention when not to use among siblings, but overall clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, but the description adds behavioral details: returns day-by-day projection, running balance, and a flag for the lowest point. It also mentions that starting_balance isn't in the CSV, which is useful context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two well-structured sentences plus a note. Every sentence is meaningful, front-loaded with purpose, and no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 optional parameters, no output schema), the description sufficiently explains purpose, parameters, return structure, and a key limitation. It is complete for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% (only starting_balance has description). The description reinforces parameter meanings and adds the important clarification that starting_balance is not present in the CSV, which is not in the schema. This adds value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool projects cash flow over N days using recurring bills and income. The verb 'project' and resource 'cash flow' are specific, and the description distinguishes it from siblings like finance_spending_by_category or finance_debt_payoff_plan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a key usage guideline about passing a real starting_balance for accuracy. While it doesn't explicitly say when not to use it or name alternatives, the context is clear and the note adds practical value.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds value by detailing the exact summary content (transaction count, date span, last import time, per-category totals), going beyond what annotations provide. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first describes the output, second gives usage guidance and notes no arguments. No extraneous words, front-loaded with purpose. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters, full annotations, and a clear description of return content, the description is complete. It lacks an explicit output schema but sufficiently explains what the tool returns. Sibling tools are diverse, but the overview tool's purpose is well-covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so schema coverage is effectively 100%. With no parameters, the description has no need to add parameter details, and the baseline score of 4 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool summarizes store data including transaction count, date span, last import time, and per-category inflows/outflows. It uses the verb 'summarize' and specifies the resource, distinguishing it from sibling tools like finance_search_transactions or finance_spending_by_category.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Call this first to know what data is available', providing clear guidance on when to use it. However, it does not explicitly mention when not to use it or list alternatives, missing a point for full marks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate read-only, idempotent, non-destructive. The description adds that it simulates and returns computed metrics (months to debt-free, total interest, date, per-debt payoff). No contradictions, and it provides sufficient behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with clear structure: first sentence states purpose and strategy options, second sentence clarifies inputs and outputs. No redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simulation tool with 3 parameters, the description covers all inputs (debts, monthly_budget, strategy) and outputs (months, interest, date, per-debt payoff). No output schema exists but return values are described. Missing error handling but acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, but the description clarifies that debts are user-provided and explains each strategy's meaning (avalanche=highest APR, snowball=smallest balance). It adds value by explaining the strategy enum beyond the enum values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool simulates a debt-payoff plan with given debts and monthly budget, specifying strategies and that debts are user-provided. It distinctly separates from sibling tools which focus on different finance functions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use (simulate payoff plans) and that debts are provided by the user (not read from CSV), indicating it's for manual scenario testing. It does not explicitly exclude alternative tools but sibling tools are unrelated, so no confusion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (destructiveHint=true, idempotentHint=true), the description adds that imported transactions and cached balances are retained, which is important behavioral context for the agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences clearly state the action and its effects, with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and no output schema, the description fully explains what the tool does and what is preserved, meeting all informational needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, and schema coverage is 100%, so the description's note of 'No args' provides no additional meaning; baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool forgets the SimpleFIN connection and clears the stored access URL, distinguishing it from the sibling tool finance_link_bank which presumably creates a connection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the name and description (use to disconnect a bank), but no explicit guidance on when to use versus alternatives or prerequisites is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds value beyond annotations: explains idempotency with 'dedupes by a stable row hash' and details return values (counts, date span, warnings). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences, front-loaded with purpose, no unnecessary words. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, description fully covers return structure and idempotency behavior. Tool is simple (1 param), and description provides all needed context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter, 'path', fully described in schema. Description merely restates the schema. Baseline 3 as per rule.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Import a Rocket Money transaction CSV export into the local store', providing a specific verb and resource. Among siblings (finance_data_overview, etc.), none perform CSV import, so it is well-distinguished.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains idempotency and the effect of re-importing, which guides usage. No explicit when-not-to-use or alternative tools, but given the sibling list, it is clear this is the only import tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description claims the tool is idempotent ('Idempotent transactions (dedupe by provider id)'), but the annotations explicitly set idempotentHint: false, creating a direct contradiction. This severely undermines the agent's ability to reason about behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise and front-loaded: first sentence states purpose, then token acquisition, then tool actions, then idempotency, then args and returns. Every sentence earns its place with no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, the description covers the token source, idempotency, side effect (durable URL), initial sync duration, and return values. Minor gap: does not explain what 'import counts' means, but sufficient for an AI.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes the setup_token parameter with coverage 100%. The description adds value by specifying how to obtain the token (link to website, account steps) and its format (base64), which aids correct usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description explicitly states 'Connect a bank via SimpleFIN Bridge for real-time balances and ongoing transaction sync', clearly defining the verb and resource, and differentiating from sibling tools like finance_import_csv and finance_search_transactions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides concrete instructions for obtaining the token ('Get a one-time setup token from bridge.simplefin.org (My Account → generate a token)') and explains that it creates a durable access URL and runs an initial sync. However, it does not explicitly exclude other tools or state when not to use it, which would be helpful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate idempotentHint=true and destructiveHint=false. Description adds that re-applying rules modifies transaction categories and returns a count, which is consistent and adds context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no wasted words. Front-loaded with the core action, then usage guidance. Perfectly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters, no output schema, and annotations covering safety, the description fully explains behavior and usage context. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters, schema coverage 100%. Description confirms 'No args.' Baseline for 0 parameters is 4; no additional guidance needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it lists and re-applies merchant→category rules, returning count of changed transactions. Distinguishes from sibling tools like add/remove category rules.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Call after editing rules to resync,' giving clear guidance on when to use. Does not explicitly mention when not to use, but siblings cover alternative actions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only and idempotent. The description adds valuable behavioral context: merchant-key normalization, cadence analysis, price hike flagging, and full return structure. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: two sentences plus a detailed return type snippet. No wasted words, front-loaded with key action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Fully complete for a no-parameter tool: describes what it does, how it works, and returns a detailed structure. No output schema, so the description carries the full burden, which it meets.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist (0 params, 100% schema coverage). Baseline 4 is appropriate; the description explicitly states 'Args: none'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool detects and lists recurring charges from transaction history using specific analysis methods. It distinguishes itself from sibling tools like finance_search_transactions or finance_spending_by_category by focusing specifically on subscriptions and recurring charges.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains it analyzes all history with no args, implying it's the go-to for subscriptions. It lacks explicit exclusions or comparisons to alternatives, but the purpose is clear given the sibling set.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, assuring safe read-only behavior. The description adds valuable behavioral details: substring matching on name/descriptor and the specific return fields (merchant, count, total_spent, etc.), which go beyond annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two sentences, front-loaded with the main action and outcome. Every word is useful, with no repetition or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple query tool with 3 params and known schema, the description covers input, output structure, and use cases. It could mention potential limitations (e.g., pagination or data range), but overall it provides sufficient context for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all 3 parameters with descriptions. The description adds that merchant is required and from/to are optional, and clarifies substring match for merchant. This adds some meaning beyond the schema but does not fully compensate for missing details (e.g., date format validation already in schema).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists every charge from a given merchant with a spend summary, specifying substring matching on name/descriptor. It distinguishes from siblings like finance_search_transactions (broader search) or finance_spending_by_category (category-level) by focusing on a single merchant.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit use cases ('how much have I paid X' and 'spotting creep'), which helps the agent determine when to use this tool. However, it does not mention alternatives or when not to use it, leaving some ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate destructive and idempotent behavior. The description adds context: transactions already recategorized are not reverted, and it returns a boolean indicating removal. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no redundant information. The purpose is front-loaded, and every sentence provides essential details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description explicitly states the return value. Side effects and parameter semantics are covered. The tool is simple and the description is fully adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole parameter 'match' is fully defined in the schema with description. The description only mentions 'Args: match' without adding new information, meeting the baseline for 100% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete'), the resource ('category rule'), and the method ('by its exact match string'). It differentiates from sibling tools like 'add_category_rule' and 'list_category_rules' by specifying deletion and exact matching.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for removing a rule by its match string but does not explicitly state when to use it versus alternatives. It mentions a side effect (transactions keep categories) but lacks guidance on when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so agent knows it's safe. Description adds key behavioral traits: newest-first pagination, signed amounts, and return structure. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence paragraph is front-loaded with purpose and flexibility. Every sentence adds value, no redundancy. Very efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description fully details the return object (total, count, offset, has_more, transactions fields). Covers ordering, pagination, and signing. Complete for a search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 78%, and the description adds extra context like absolute value filtering for amounts and substring matching for merchant. It succinctly explains each parameter's semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Search transactions with filters' and lists specific filterable attributes. Distinguishes from siblings as it is the only general transaction search tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Indicates all filters are optional and combinable, implying broad applicability. However, does not explicitly advise when to use alternatives like finance_spending_by_category or finance_merchant_history, which are listed as siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds behavioral details: default date range behavior, sorting order, and the exact return structure. This enhances transparency beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the purpose, parameters, and output structure. Every element is necessary, and the critical information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only aggregation tool with two optional parameters and no output schema, the description fully specifies the return format including the list of categories with fields and total values. No gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both parameters described. The description only repeats the format (YYYY-MM-DD) and confirms they are optional, adding no new semantic meaning beyond the schema. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool groups inflow and outflow by category over an optional date range, sorted by outflow descending. This distinguishes it from siblings like finance_search_transactions (detailed search) or finance_data_overview (broader overview), providing a specific verb and resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies that the date range is optional (defaults to all history) and that results are sorted by outflow descending. While it doesn't explicitly compare to alternatives, the context is clear enough for an agent to infer when to use this tool for aggregated category data.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses side effect (refreshing balances), deduplication by provider id, and default non-re-pull behavior. Annotations do not provide such details, so description adds valuable transparency. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences plus args/return notes, no fluff. Front-loaded with purpose, then default behavior, dedup, prerequisite, and structured args/return summary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, default vs override, deduplication, prerequisite, and return fields (accounts, newTransactions, store_span) despite no output schema. Missing: behavior when no prior transactions exist, but overall sufficient for a simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with description. The tool description adds context: default behavior (since last stored transaction) and an example (365 for full refresh), which goes beyond the schema's 'Override' description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool pulls new transactions and refreshes balances from SimpleFIN. Distinguishes from sibling tools like finance_import_csv (CSV import) and finance_balances (just balances) by specifying the source and action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains default incremental behavior (from day after latest transaction) and when to use days_back for full refresh. Mentions prerequisite finance_link_bank. Does not explicitly state when not to use, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.